Research Article
Exploring Self-attention Mechanism of Deep Learning in Cloud Intrusion Detection
@INPROCEEDINGS{10.1007/978-3-030-69992-5_5, author={Chenmao Lu and Hong-Ning Dai and Junhao Zhou and Hao Wang}, title={Exploring Self-attention Mechanism of Deep Learning in Cloud Intrusion Detection}, proceedings={Cloud Computing. 10th EAI International Conference, CloudComp 2020, Qufu, China, December 11-12, 2020, Proceedings}, proceedings_a={CLOUDCOMP}, year={2021}, month={2}, keywords={Deep learning Convolution neural network Self-attention Long short-term memory Network intrusion detection}, doi={10.1007/978-3-030-69992-5_5} }- Chenmao Lu
Hong-Ning Dai
Junhao Zhou
Hao Wang
Year: 2021
Exploring Self-attention Mechanism of Deep Learning in Cloud Intrusion Detection
CLOUDCOMP
Springer
DOI: 10.1007/978-3-030-69992-5_5
Abstract
Cloud computing offers elastic and ubiquitous computing services, thereby receiving extensive attention recently. However, cloud servers have also become the targets of malicious attacks or hackers due to the centralization of data storage and computing facilities. Most intrusion attacks to cloud servers are often originated from inner or external networks. Intrusion detection is a prerequisite to designing anti-intrusion countermeasures of cloud systems. In this paper, we explore deep learning algorithms to design intrusion detection methods. In particular, we present a deep learning-based method with the integration of conventional neural networks, self-attention mechanism, and Long short-term memory (LSTM), namely CNN-A-LSTM to detect intrusion. CNN-A-LSTM leverages the merits of CNN in processing local correlation data and extracting features, the time feature extracting capability of LSTM, and the self-attention mechanism to better exact features. We conduct extensive experiments on the KDDcup99 dataset to evaluate the performance of our CNN-A-LSTM model. Compared with other machine learning and deep learning models, our CNN-A-LSTM has superior performance.
